This disclosure is directed to a touchless interactive environment. An input device may be configured to capture electronic images corresponding to physical objects detectable within a physical three-dimensional region. A computer system may establish a virtual three-dimensional region mapped to the physical three-dimensional region, with the virtual three-dimensional region defining a space where a plurality of virtual objects are instantiated based on the plurality of electronic images. The computer system may select a virtual object from the plurality of virtual objects as one or more commanding objects, with the one or more commanding objects indicating a command of a graphical user interface to be performed based on a position of the one or more commanding objects. The computer system may then perform the command of the graphical user interface based on the position of the one or more commanding objects.